检索结果-内蒙古大学图书馆

Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL-IJCNLP 2021

作者： Chen, Wenqing Tian, Jidong Li, Yitian He, Hao Jin, Yaohui MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University China State Key Lab of Advanced Optical Communication System and Network Shanghai Jiao Tong University China

ISBN: (纸本)9781954085527

Logical table-to-text generation aims to automatically generate fluent and logically faithful text from tables. The task remains challenging where deep learning models often generated linguistically fluent but logically inconsistent text. The underlying reason may be that deep learning models often capture surface-level spurious correlations rather than the causal relationships between the table x and the sentence y. Specifically, in the training stage, a model can get a low empirical loss without understanding x and use spurious statistical cues instead. In this paper, we propose a de-confounded variational encoder-decoder (DCVED) based on causal intervention, learning the objective p(y|do(x)). Firstly, we propose to use variational inference to estimate the confounders in the latent space and cooperate with the causal intervention based on Pearl's do-calculus to alleviate the spurious correlations. Secondly, to make the latent confounder meaningful, we propose a back-prediction process to predict the not-used entities but linguistically similar to the exactly selected ones. Finally, since our variational model can generate multiple candidates, we train a table-text selector to find out the best candidate sentence for the given table. An extensive set of experiments show that our model outperforms the baselines and achieves new state-of-the-art performance on two logical table-to-text datasets in terms of logical fidelity. © 2021 Association for Computational Linguistics

关键词： Calculations

来源：评论

学校读者我要写书评

暂无评论

To What Extent Do Natural Language Understanding Datasets Correlate to Logical Reasoning? A Method for Diagnosing Logical Reasoning 29

To What Extent Do Natural Language Understanding Datasets Co...

引用

29th International Conference on Computational Linguistics, COLING 2022

作者： Li, Yitian Tian, Jidong Chen, Wenqing Fan, Caoyun He, Hao Jin, Yaohui MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University China State Key Lab of Advanced Optical Communication System and Network Shanghai Jiao Tong University China

Reasoning and knowledge-related skills are considered as two fundamental skills for natural language understanding (NLU) tasks such as machine reading comprehension (MRC) and natural language inference (NLI). However, it is not clear to what extent an NLU task defined on a dataset correlates to a specific NLU skill. On the one hand, evaluating the correlation requires an understanding of the significance of the NLU skill in a dataset. Significance judges whether a dataset includes sufficient material to help the model master this skill. On the other hand, it is also necessary to evaluate the dependence of the task on the NLU skill. Dependence is a measure of how much the task defined on a dataset depends on the skill. In this paper, we propose a systematic method to diagnose the correlations between an NLU dataset and a specific skill, and then take a fundamental reasoning skill, logical reasoning, as an example for analysis. The method adopts a qualitative indicator to indicate the significance while adopting a quantitative indicator to measure the dependence. We perform diagnosis on 8 MRC datasets (including two types) and 3 NLI datasets and acquire intuitively reasonable results. We then perform the analysis to further understand the results and the proposed indicators. Based on the analysis, although the diagnostic method has some limitations, it is still an effective method to perform a basic diagnosis of the correlation between the dataset and logical reasoning skill, which also can be generalized to other NLU skills. © 2022 Proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Architecture and performance of a bidirectional OXC based on reversible optical switches with reduced complexity 33

Architecture and performance of a bidirectional OXC based on...

引用

2007 33rd European Conference and Exhibition of Optical communication, ECOC 2007

作者： Qi, Yongmin Hu, Weisheng Dong, Yi Zhong, Wen-De Xu, Xinyu He, Hao Jin, Yaohui Guo, Wei Sun, Weiqiang Xiao, Shilin Su, Yikai State Key Lab. of Advanced Optical Communication System and Network Shanghai JiaoTong University Shanghai200240 China Network Technology Research Centre Nanyang Technological University Singapore639798 Singapore

By exploiting the symmetry of bidirectional wavelength-connections in WDM networks, we propose an NxN bidirectional OXC using one N/2xN/2 reversible optical switch to reduce the complexity of the OXCs. The feasibility... 详细信息

ISBN: (纸本)9783800730421

关键词： Optical switches

来源：评论

学校读者我要写书评

暂无评论

Micro-Bending Influence on Mode-Dependent Loss 15

Micro-Bending Influence on Mode-Dependent Loss

引用

15th IEEE International Conference on Advanced Infocomm Technology, ICAIT 2023

作者： Liang, Junpeng Qiao, Gang Wei, Jinlong Li, Juhao Yang, Yu Xu, Zhaopeng Liu, Lulu Wang, Shangcheng Wu, Qi Hu, Weisheng Peng Cheng Laboratory Dept. of Circuits and System Shenzhen China Peking University State Key Lab of Advanced Optical Communication Systems and Network Beijing China

ISBN: (纸本)9798350314120

Micro-bending with random curvature is usually used to model the mode coupling in few mode fiber (FMF). However, previous models overlooked the accompanied mode dependent loss (MDL) and neglected the order constraints of coupling loss between different modes. In this work, we calculate out the accompanied loss of each mode by using the finite element method. The results show that MDL always increases with bending curvature due to the high-order modes have larger loss than low-order modes. This observation has been confirmed by experiments. Finally, we compare the multi-segment FMFs model with and without considering the accompanied MDL, the results show that micro-bending would degrade the system performance especially when considering the accompanied MDL. © 2023 IEEE.

关键词： MEMS

来源：评论

学校读者我要写书评

暂无评论

Research on stochastic comb-pilot design for NC-OFDM system

Research on stochastic comb-pilot design for NC-OFDM system

引用

2008 International Conference on Wireless communications, networking and Mobile Computing, WiCOM 2008

作者： Xuetao, Dong Xianzhong, Xie Institute of Personal Communication MII Key Lab on Mobile Communication CQUPT Chongqing 400065 China National Defense Key Laboratory of Telecommunication System Information and Control Technology NO.36 Institute of CETC Jiaxing 314033 China

ISBN: (纸本)9781424421084

NC-OFDM is OFDM-based spectrum pooling technique and also a transmission mode of cognitive radio. The paper models and analyzes NC-OFDM stochastic process, then designs stochastic comb-pilot pattern and analyzes its characteristics in detail. At the end of the paper simulation results prove the feasibilities of the stochastic comb-pilot strategies in NC-OFDM system. © 2008 IEEE.

关键词： Orthogonal frequency division multiplexing

来源：评论

学校读者我要写书评

暂无评论

Two-Stage Topic Sentence Extraction for Chinese Student Essays 12th

Two-Stage Topic Sentence Extraction for Chinese Student Ess...

引用

12th National CCF Conference on Natural Language Processing and Chinese Computing, NLPCC 2023

作者： Dong, Yuwu Zheng, Feiran Chen, Hongyu Ding, Yizhou Zhou, Yifan He, Hao MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai China State Key Lab of Advanced Optical Communication System and Network Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9783031446986

In this paper, we present the method proposed by our team for Track 2 of NLPCC 2023 Shared Task 7, which focuses on the extraction of paragraph-level and whole essay topic sentences in middle school student essays. This paper proposes a two-stage topic sentence extraction framework for each paragraph and the whole essay. In the first stage, we extract topic sentences for each paragraph, considering local semantic and contextual aspects. In the second stage, we derive the text topic sentence for the whole essay from the extracted paragraph-level topic sentences. Compared with the one-stage method, the two-stage method which can focus on the local semantic information of paragraphs related to the task has advantages in paragraph and full-text topic sentence extraction. Comparative experiments show that the extraction performance of the fine-tuned two-stage topic sentence extraction framework surpasses the few-shot large language models (GPT-3.5 et al.). The final comprehensive index also achieved the first-place result in this track. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A technique for blind identification of uplink signals in multibeam smart antenna

A technique for blind identification of uplink signals in mu...

引用

4th Advanced International Conference on Telecommunications, AICT 2008

作者： Chen, Qinghua Xie, Xianzhong Institute of Personal Communication MII Key Lab of Mobile Communication Technology Chongqing University of Posts and Telecommunications Chongqing 400065 China National Defense Key Laboratory of Telecommunication System Information and Control Technology Jiaxing 314033 China

ISBN: (纸本)9780769531625

In this paper, we construct signal modelings of four types of signals in wireless communication, i.e. single user single antenna signal, virtual MIMO signal, multibeam smart antenna signal and single user MIMO signal first , based on the model, propose a technique for blind identification of uplink signals in multibeam smart antenna by combining MUSIC algorithm with Forward-backward Spatial Smoothing algorithm to blindly estimate DOAs of these four types of signals, when the source signal is one of the four types. Simulation results show the feasibility of this technique. This paper has important value in both theory and application, especially in noncooperation communication environment. © 2008 IEEE.

关键词： Multiple signal classification

来源：评论

学校读者我要写书评

暂无评论

User Demand Behavior Based Adaptive Algorithm for Service Composition of Streaming Media

User Demand Behavior Based Adaptive Algorithm for Service Co...

引用

International Symposium on Intelligent Information Technology Application, IITA

作者： Liyue Zhu Jian Yang Han Hu Hongsheng Xi Key Laboratory of Network Communication System and Control Chinese Academy of Sciences Key Laboratory of Anhui Network Communication System and Control Department of Automation University of Science and Technology Hefei Anhui China

ISBN: (纸本)9781424452125

Service composition is a technique to recompose various heterogeneous network services for a new business. A modern streaming media system may run multiple businesses. Their resources can easily be improperly distributed and under utilized. This paper studies service composition in the context of streaming media applications. A three-layer model is adopted to describe the system. The optimal service composition is formulated as a constraint optimization problem. By applying linear programming to the proposed cost function, a user demand behavior based adaptive algorithm (UDBA) for service composition is presented. The simulation results show that our UDBA algorithm improves the performance of the streaming media system.

关键词： Adaptive algorithm Streaming media TV network servers control systems Web and internet services Web services Clustering algorithms Automatic control communication system control

来源：评论

学校读者我要写书评

暂无评论

Chaos characteristics analysis of transient signals for phase-locked synthesizer based FHC system 14

Chaos characteristics analysis of transient signals for phas...

引用

14th International Symposium on communications and Information Technologies, ISCIT 2014

作者： Ping, Li Guohong, Wang Yan, Xiaopeng Peng, Gong Shi, Wenbo Chunyun, Song Beijing Institute of Technology National Key Lab. of Mechatronic Engineering and Control Beijing100081 China Northeastern University School of Computer and Communication Engineering Qinhuangdao China National Lab. of Information Control Technology for Communication System Jiaxing Zhejiang314033 China

ISBN: (纸本)9781479944163

Frequency synthesizer plays an important role in frequency hopping communication system. In this paper, we derivate the conditions for a system to become the chaotic based on the phase model of phase-locked synthesizer. We found that the system parameter changing during the frequency switching is able to make the system to be chaotic. Based on the Cao's method [5], we find that the fractal dimension of the transient signals should be equal to or less than 4, which also provides the maximal positive Lyapunov exponent. In addition, the unique double-ring attractor of them is also reproduced through the phase reconstruction, which also implies that the frequency switching will result in a chaotic for Frequency-Hopping communication system. © 2014 IEEE.

关键词： Fractal dimension

来源：评论

学校读者我要写书评

暂无评论

Collaboration filtering recommendation optimization with user implicit feedback

引用

Journal of Computational Information systems 2014年第14期10卷 5855-5862页

作者： Cui, Haomin Zhu, Ming Joint Laboratory of Network Communication System & Control Key Lab of Anhui Department of Automation University of Science and Technology of China Hefei China

Collaboration Filter is one of well-known effective methods for recommendation. The suggestions are based on the mass of user ratings for various items, which are used as explicit feedback. However, implicit feedback such as the time spent on website, how soon the user skipped the song, and the sequence of selected items have also proved to be useful in recommender systems. In this paper, we proposed a hybrid recommendation algorithm considering both explicit and implicit feedback to produce better recommended list. An iteration process is proposed for using implicit feedback in order to find effective feedback for recommendation. Time window is also used to limit the impact range of implicit feedback. Experimental results on MovieLens datasets show that the implicit feedback can effectively compensate for the shortcomings of explicit feedback and the proposed algorithm is more accurate than the traditional one. © 2014 by Binary Information Press

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：